Systems and methods for generating and using anthropomorphic signatures to authenticate users

Abstract

The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.

We claim as follows: 
     
       1. A computer-implemented method of authentication using a plurality of non-deterministic authentication biometric inputs, the method including:
 receiving a plurality of non-deterministic biometric inputs with a request for authentication; 
 feeding the non-deterministic biometric inputs to a trained machine learning model and generating a set of authentication feature vectors, wherein the non-deterministic authentication biometric input includes an image and a voice sample of a user; 
 projecting the set of feature vectors onto a surface of a hyper-sphere; and 
 authenticating the user when a cosine distance between authentication feature vectors in the set of authentication feature vectors and a characteristic identity vector previously registered for the user is less than a pre-determined threshold, wherein the characteristic identity vector for the user is determined by averaging feature vectors for a plurality of images and for a plurality of voice samples of the user. 
 
     
     
       2. The method of  claim 1 , wherein the sets of feature vectors are projected onto a surface of a unit hyper-sphere. 
     
     
       3. The method of  claim 1 , wherein the characteristic identity vector for the user was determined by averaging feature vectors for a plurality of images and for a plurality of voice samples on a user-by-user basis. 
     
     
       4. The method of  claim 3 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples on a user-by-user basis. 
     
     
       5. The method of  claim 3 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples for classes of users. 
     
     
       6. The method of  claim 3 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples across users. 
     
     
       7. A non-transitory computer readable storage medium impressed with computer program instructions to authenticate using a plurality of non-deterministic authentication biometric inputs, the instructions, when executed on a processor, implement a method comprising:
 receiving a plurality of non-deterministic biometric inputs with a request for authentication; 
 feeding the non-deterministic biometric inputs to a trained machine learning model and generating a set of authentication feature vectors, wherein the non-deterministic authentication biometric input includes an image and a voice sample of a user; 
 projecting the set of feature vectors onto a surface of a hyper-sphere; and 
 authenticating the user when a cosine distance between authentication feature vectors in the set of authentication feature vectors and a characteristic identity vector previously registered for the user is less than a pre-determined threshold, wherein the characteristic identity vector for the user is determined by averaging feature vectors for a plurality of images and for a plurality of voice samples of the user. 
 
     
     
       8. The non-transitory computer readable storage medium of  claim 7 , wherein the sets of feature vectors are projected onto a surface of a unit hyper-sphere. 
     
     
       9. The non-transitory computer readable storage medium of  claim 7 , wherein the characteristic identity vector for the user was determined by averaging feature vectors for a plurality of images and for a plurality of voice samples on a user-by-user basis. 
     
     
       10. The non-transitory computer readable storage medium of  claim 9 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples on a user-by-user basis. 
     
     
       11. The non-transitory computer readable storage medium of  claim 9 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples for classes of users. 
     
     
       12. The non-transitory computer readable storage medium of  claim 9 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples across users. 
     
     
       13. A system including one or more processors coupled to memory, the memory loaded with computer instructions to authenticate using a plurality of non-deterministic authentication biometric inputs, when executed on the processors implement the instructions as follows:
 receiving a plurality of non-deterministic biometric inputs with a request for authentication; 
 feeding the non-deterministic biometric inputs to a trained machine learning model and generating a set of authentication feature vectors, wherein the non-deterministic authentication biometric input includes an image and a voice sample of a user; 
 projecting the set of feature vectors onto a surface of a hyper-sphere; and 
 authenticating the user when a cosine distance between authentication feature vectors in the set of authentication feature vectors and a characteristic identity vector previously registered for the user is less than a pre-determined threshold, wherein the characteristic identity vector for the user is determined by averaging feature vectors for a plurality of images and for a plurality of voice samples of the user. 
 
     
     
       14. The system of  claim 13 , wherein the sets of feature vectors are projected onto a surface of a unit hyper-sphere. 
     
     
       15. The system of  claim 13 , wherein the characteristic identity vector for the user was determined by averaging feature vectors for a plurality of images and for a plurality of voice samples on a user-by-user basis. 
     
     
       16. The system of  claim 15 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples on a user-by-user basis. 
     
     
       17. The system of  claim 15 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples for classes of users. 
     
     
       18. The system of  claim 15 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples across users.